News and Announcements
ARTICLE
Seismic multi-attribute fusion using fast independent component analysis and its application
MIN ZHAO1 ,
YUQING WANG1,2 ,
ZHENMING PENG1,2 ,
HAO WU1,2 ,
YANMIN HE1,2 ,
JINGJING ZHOU3 ,
LIFENG YANG1
Show Less
1
School of Optoelectronic Information, University of Electronic Science and Technology of China, Chengdu 610054, P.R. China.,
2
Center for Information Geoscience, University of Electronic Science and Technology of China, Chengdu 610054, P.R. China.,
3
CNPC Sichuan Petroleum Geophysical Prospecting Company, Chengdu 610213, P.R. China.,
JSE 2019, 28(1), 89–101;
Submitted: 23 March 2018 | Accepted: 4 November 2018 | Published: 1 February 2019
© 2019 by the Authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract
Zhao, M., Wang, Y.Q., Peng, Z.M., Wu, H., He, Y.M., Zhou, J.J. and Yang, L.F., 2019. Seismic multi-attribute fusion using fast independent component analysis and its application. Journal of Seismic Exploration, 28: 89-101. Basic principles of independent component analysis (ICA) and fast independent component analysis (FastICA) algorithm are elaborated, and we propose an automatic fusion method of seismic multi-attribute based on FastICA. This method can calculate the transform kernel matrix rapidly using FastICA algorithm to achieve the feature fusion of several seismic attributes in the ICA domain. After that we map the synthesized attribute to the spatial domain to obtain the fusion result. Our method can remove the correlation hidden in high-order statistical characteristics between features. Finally, the application of 3D seismic data in northeastern Sichuan shows the effectiveness and rationality of the proposed method.
Keywords
ICA/FastICA
transform kernel matrix
feature fusion
seismic attributes
References
- Blanco, D. and Mulgrew, B., 2005. ICA in signals with multiplicative noise. IEEETransact. Sign. Process., 53: 2648-2657.
- Chien, J.T. and Hsieh, H.L., 2012. Convex divergence ICA for blind source separation.
- IEEE Transact. Audio Speech Lang. Process., 20: 302-313.
- Dontchev, A.L. and Rockefeller, R.T., 2010. Newton's Method for Generalized
- Equations: a Sequential Implicit Function Theorem. Mathematical Programming,123: 139-159.
- Eriksson, J. and Koivunen, V., 2006. Complex random vectors and ICA models:
- Identifiability, uniqueness, and eparability. IEEE Transact. Inform. Theory, 52:1017-1029.
- Hyvarinen, A., 1997. A family of fixed-point algorithms for independent componentanalysis. IEEE Internat. Conf. Acoust. Speech Signal Process., 5: 3917-3920.
- Hyvarinen, A., 1999. Fast and robust fixed-point algorithms for independent componentanalysis. IEEE Transact. Neural Netw., 10: 626-634.
- Jutten, C. and Herault, J., 1988. Une solution neuromimétique au probleme de séparationde sources. Traitem. Signal, 5: 389-403.
- Jha, S.K. and Yadava, R.D.S., 2011. Denoising by singular value decomposition and itsapplication to electronic noise data processing. IEEE Sensors J., 11: 35-43.
- Kim, Y.G., Song, Y.J., Chang, U.D. and Kim, D.W., 2008.. Face recognition using afusion method based on bidirectional 2DPCA. Appl. Mathemat. Computat., 205:601-607.
- Li, Q.Z., Peng, Z.M., Zhou, J.J. and Zhang, P., 2014. Seismic multi-attribute fusion basedon pulse coupled neural networks. Oil Geophys. Prosp., 49: 316-321.
- Malek, A. and Yashtini, M., 2010. Image fusion algorithms for color and gray levelimages based on LCLS method and novel artificial neural network: Neurocomput.,73: 937-943.
- Margadan-Mendez, M., Juslin, A., Nesterov, S.V. and Kalliokoski, K., 2010. ICA basedautomatic segmentation of dynamic H,°O cardiac PET images. IEEE Transact.Inform. Technol. Biomed., 14: 795-802.
- Mitianoudis, N. and Stathaki, T., 2007. Pixel-based and region-based image fusionschemes using ICA bases. Informat. Fusion, 8: 131-142.
- Primlos, J.A. and Giannelli, M., 2001. Kuhn-Tucker-based stability conditions forsystems with saturation. IEEE Transact. Automat. Contr., 46: 1643-1647.
- Raeesi, M., Moradzadeh, A., Doulati Ardejani, F. and Rahimi, M., 2012. Classificationand identification of hydrocarbon reservoir lithofacies and their heterogeneityusing seismic attributes, logs data and artificial neural networks. J. Petrol. Sci.Engineer., 82: 151-165.
- Rezvandehy, M., Aghababaei, H. and Raissi, S. H., 2011. Integrating seismic attributes inthe accurate modeling of geological structures and determining the storage of thegas reservoir in Gorgan Plain (North of Iran). J. Appl. Geophys., 73: 187-195.
- Stokman, H. and Gevers,T., 2007. Selection and fusion of color models for image featuredetection. IEEE Transact. Patt. Analys. Mach. Intellig., 29: 371-381.
- Shen, H., Kleinsteuber, M. and Huper, K., 2008. Local convergence analysis of FastICAand related algorithms. IEEE Transact. Neural Netw., 19: 1022-1032.
- Unser, M., Sage, D. and Van De Ville, D., 2009. Multiresolution monogenic signalanalysis using the Riesz-Laplace wavelet transform. IEEE Transact. ImageProcess., 18: 2402-2417.
- Xie, C.F., Peng, Z.M., Zhou, J.J., Zhang, P. and Zhang, W., 2014. Seismic multi-attributefusion based on contourlet transform. Oil Geophys. Prosp., 49: 739-744.
- Yang, J., Zhang, D. and Yang, J., 2007. Constructing PCA baseline algorithms toreevaluate ICA-based face-recognition performance. IEEE Transact., Man,Cybernet., Part B (Cybernetics), 37: 1015-1020.
- Zheng, Y., Qin, Z., Shao, L. and Hou, X., 2008. A novel objective image quality metricfor image fusion based on Renyi entropy. Informat. Technol., 7: 930-935.
